CN109060143B - Pig body temperature monitoring system and method based on thermal infrared technology - Google Patents
Pig body temperature monitoring system and method based on thermal infrared technology Download PDFInfo
- Publication number
- CN109060143B CN109060143B CN201810932394.2A CN201810932394A CN109060143B CN 109060143 B CN109060143 B CN 109060143B CN 201810932394 A CN201810932394 A CN 201810932394A CN 109060143 B CN109060143 B CN 109060143B
- Authority
- CN
- China
- Prior art keywords
- temperature
- classifier
- sensor
- thermal infrared
- body temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036760 body temperature Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 title claims abstract description 12
- 238000005516 engineering process Methods 0.000 title claims abstract description 11
- 230000007613 environmental effect Effects 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000009395 breeding Methods 0.000 claims abstract description 9
- 230000001488 breeding effect Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 18
- 238000005286 illumination Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 241001465754 Metazoa Species 0.000 abstract description 6
- 241000282887 Suidae Species 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 244000144972 livestock Species 0.000 abstract description 2
- 244000144977 poultry Species 0.000 abstract description 2
- 210000000436 anus Anatomy 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 210000000936 intestine Anatomy 0.000 description 3
- 206010011409 Cross infection Diseases 0.000 description 2
- 206010029803 Nosocomial infection Diseases 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 210000005069 ears Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002550 fecal effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/20—Clinical contact thermometers for use with humans or animals
- G01K13/223—Infrared clinical thermometers, e.g. tympanic
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Processing (AREA)
- Radiation Pyrometers (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a pig body temperature monitoring system based on a thermal infrared technology, which comprises: MCU core chip, image preprocessing module, trinity sensor, thermal infrared imager, switch, high in the clouds server, mobile terminal, electronic computer, MCU core chip is connected to trinity sensor and environmental information collection is realized, thermal infrared imager connects image preprocessing module and realizes image acquisition, and MCU core chip and image preprocessing module pass through the switch and upload information to high in the clouds server, and the high in the clouds server still connects mobile terminal and electronic computer respectively to its distribution information. The invention relates to a non-contact non-invasive body temperature detection system, which can indirectly acquire body temperature data with high accuracy under the condition of not damaging the body and normal life and work of an animal. Compared with the traditional body temperature measuring method which is easy to cause the stress reaction of the breeding pigs, the method is more in line with the livestock and poultry welfare breeding concept.
Description
Technical Field
The invention relates to the field of pig welfare breeding, the field of sensors and the field of algorithm research, in particular to a pig body temperature monitoring system and method based on a thermal infrared technology.
Background
With the rapid development of the breeding industry and the animal husbandry and the accelerated development of the industrial intelligence, the traditional breeding and animal husbandry gradually develops towards novel and modern intelligent breeding and animal husbandry. The welfare cultivation is taken as a final target, the cultivation and animal husbandry is greatly developed by combining the modern intelligent technology, the technical innovation is promoted, and the labor force is liberated.
As the first major country for producing pork in China, the farms basically depend on the coordination of a large number of workers to carry out daily feeding work, and the intensive and intelligent degree is very low, which does not accord with the current development trend. The disease early warning of live pigs by field personnel mostly depends on human observation and experience judgment, such as diet conditions, fecal states and the like, and is measured by a thermometer after the abnormality occurs. The traditional methods of measuring by a common thermometer and the like have the defects of long time consumption, easy breakage, easy generation of cross infection and the like.
Disclosure of Invention
The invention provides a pig body temperature monitoring system and method based on a thermal infrared technology, aiming at the problems in the background technology.
The technical scheme is as follows:
the invention firstly discloses a pig body temperature monitoring system based on a thermal infrared technology, which comprises: MCU core chip, image preprocessing module, trinity sensor, thermal infrared imager, switch, high in the clouds server, mobile terminal, electronic computer, MCU core chip is connected to trinity sensor and environmental information collection is realized to the acquisition of sensor, thermal infrared imager connects image preprocessing module and realizes image acquisition, and MCU core chip and image preprocessing module pass through the switch and upload information to cloud end server, and the high in the clouds server still connects mobile terminal and electronic computer respectively and distributes information to it, and wherein three-in-one sensor and thermal infrared imager are installed on supporting structure.
Specifically, the support structure comprises a support, a longitudinal adjusting knob and a transverse adjusting knob, the support comprises a base, a longitudinal telescopic rod and a transverse telescopic rod, the bottom of the longitudinal telescopic rod is fixed on the base, the top of the longitudinal telescopic rod supports the transverse telescopic rod, and the longitudinal adjusting knob is arranged on the longitudinal telescopic rod and used for adjusting the longitudinal height of the support; the transverse adjusting knob is arranged on the transverse telescopic rod and used for adjusting the transverse length of the bracket; the three-in-one sensor is arranged at the lower part of the longitudinal telescopic rod, and the thermal infrared imager is arranged at the extending tail end of the transverse telescopic rod; the three-in-one sensor is a temperature sensor, a humidity sensor and an illumination sensor.
Specifically, the three-in-one sensor takes an MSP430F149 chip as a core, and is welded with a DHT11 temperature and humidity sensor and a BH1750FVI illumination sensor.
The invention also discloses a pig body temperature monitoring method based on the thermal infrared technology, and the system comprises the following steps:
s1, acquiring environmental information through a three-in-one sensor;
s2, acquiring image information through a thermal infrared imager;
s2-1, identifying pig ears;
s2-2, extracting surface temperature, and taking the highest temperature of the identified pig ear area as the body surface temperature TbStoring the data into a database and marking time;
s3, estimating the body temperature by comprehensively acquiring environmental information and the ear temperature by using the multi-parameter body temperature inversion model;
and S4, storing the data in the server database and feeding the data back to the client for information display.
Specifically, the pig ear identification process in S2-1 is as follows:
s2-1-1, inputting an image;
s2-1-2, scanning a window;
s2-1-3, performing feature selection and extraction on the image;
s2-1-4, inputting the extracted information into a classifier, wherein the classifier is formed by the following steps: firstly, selecting a large number of training samples including a positive sample of a pig ear and a negative sample of a non-pig ear, wherein the positive samples are gray level images with the same pixel size; selecting and extracting the characteristics of the samples, and training to form a classifier;
and S2-1-5, outputting a classification result.
Specifically, the classifier training step includes:
i training the weak classifier repeatedly to become an optimal weak classifier, and the mathematical structure is as follows:
wherein x represents sub-window image data obtained by step S2-1-2; f represents a characteristic value obtained by step S2-1-3; p represents the direction of indicating the unequal sign, theta represents a threshold value, the four components are equivalent to a decision tree, and a proper classifier threshold value theta is searched in continuous training; f (x) is a feature function, which is known in the specific case.
ii, combining the optimal weak classifiers obtained in the step i to form a strong classifier, wherein the combination mode is as follows:
wherein T is the maximum iteration number of training,
ht(x) For the optimal weak classifier obtained in step i, etAnd for the weighted error value after each training, continuously weighting and averaging according to the error rate of the weak classifier, and synthesizing the multistage strong classifier to form a cascade classifier with high accuracy, wherein the cascade classifier is used as a final target Haar classifier.
Specifically, the inversion body temperature model in S3 is:
Tr＝C+αTi+βHi+γIi+θTb
in the formula, TrThe temperature values of the anus and the intestine, alpha, beta and gamma, which are output by the system, are respectivelyIs the ambient temperature TiAmbient humidity HiAmbient lighting IiThe ambient temperature T, the ambient temperature TiAmbient humidity HiAmbient lighting IiAll are measured by a three-in-one sensor; c is the compensation quantity of the pre-estimated body temperature and is determined by linear fitting; theta is the body surface temperature TbThe theta is obtained by linear fitting, the body surface temperature TbMeasured by a thermal infrared imager.
Specifically, after inputting the environmental temperature, the environmental humidity, the environmental illumination and the body surface temperature data through SPSS software, proposing an assumption, establishing a multiple logistic regression, and then performing parameter verification to finally obtain the values of the weight coefficients alpha, beta and gamma.
Specifically, the environmental impact factor p ═ α T is obtained by SPSS softwarei+βHi+γIiAll the body surface temperatures T are measuredbAdding an environmental influence factor p to obtain a corrected temperature T of the body surfacec(ii) a Respectively establishing TcFitting straight lines of the model and a scatter diagram fitting straight line actually measured by the anorectal temperature; fine tuning TcThe fitting straight line of the temperature sensor is used as an inversion temperature straight line, so that the fitting degree of the inversion temperature straight line and the fitting straight line of the actual measurement of the temperature of the anus and the intestine is maximum; at this time, TcHas a fitting straight line intercept of C value, TcThe slope of the fitted line of (2) is the value of θ.
The invention has the advantages of
(1) The invention is a real non-contact non-invasive body temperature detection system, which can indirectly acquire body temperature data with high accuracy under the condition of not damaging the body and normal life and rest of an animal. Compared with the traditional body temperature measuring method which is easy to cause the stress reaction of the breeding pigs, the method is more in line with the livestock and poultry welfare breeding concept.
(2) The invention is safe and pollution-free, can not cause cross infection which can be caused by the traditional thermometer, and has the advantages of simple installation, convenient use, high automation degree and low maintenance cost.
(3) The invention can also detect the temperature environment, assist the staff to regulate and control the indoor environment, has high temperature judgment speed, saves the field workload and improves the efficiency of the staff.
Drawings
FIG. 1 is a system block diagram of the present invention.
FIG. 2 is a system framework of the present invention.
FIG. 3 is a diagram of a three-in-one sensor base unit of the present invention.
Fig. 4 is a schematic view of the stent structure of the present invention.
FIG. 5 is a block diagram of a target detection process according to the present invention.
Detailed Description
The invention is further illustrated by the following examples, without limiting the scope of the invention:
with reference to fig. 1 and 2, the system comprises: MCU core chip, image preprocessing module, trinity sensor 2, thermal infrared imager 5, switch, high in the clouds server, mobile terminal, electronic computer, MCU core chip is connected to trinity sensor 2 and environmental information collection is realized to the MCU core chip, thermal infrared imager 5 is connected image preprocessing module and is realized image acquisition, and MCU core chip and image preprocessing module pass through the switch and upload information to the high in the clouds server, and the high in the clouds server still connects mobile terminal and electronic computer respectively and distributes information to it, and wherein trinity sensor 2 and thermal infrared imager 5 are installed on supporting structure. The image that thermal infrared imager 5 will be grabbed and the data that trinity sensor 2 gathered are uploaded to the high in the clouds server through the switch to calculate the result through the procedure of settling at the server, this procedure possesses the body temperature of pig ear discernment and the linear fitting of pluralism and predicts, can feed back to mobile terminal or electronic computer through the network and carry out result display and body temperature curve drawing etc..
Referring to fig. 3, the triad sensor 2 is based on an MSP430F149 chip and is welded with a DHT11 humidity sensor and a BH1750FVI illumination sensor. After the system is powered on and started, the three sensors are controlled to collect data, and the data are sent to the cloud server through the switch. In order to save server expenses, environmental data are collected and uploaded once every 1 minute. By drawing the change curve of each parameter, the trend is obtained, if two points with larger gradient are allowed to be processed smoothly, and finally, the improper data is obtained due to larger error is avoided. Besides monitoring the frequency of field data transmission, if abnormal information transmission occurs, the working personnel is reminded to check the switch and other network links, and the real-time performance of data uploading is guaranteed.
Referring to fig. 4, the support structure includes a support 1, a longitudinal adjusting knob 3, and a transverse adjusting knob 4, the support 1 includes a base 1-1, a longitudinal telescopic rod 1-2, and a transverse telescopic rod 1-3, the bottom of the longitudinal telescopic rod 1-2 is fixed on the base 1-1, the top of the longitudinal telescopic rod 1-2 supports the transverse telescopic rod 1-3, and the longitudinal adjusting knob 3 is disposed on the longitudinal telescopic rod 1-2 for adjusting the longitudinal height of the support 1; the transverse adjusting knob 4 is arranged on the transverse telescopic rods 1-3 and used for adjusting the transverse length of the bracket 1; the three-in-one sensor 2 is arranged at the lower part of the longitudinal telescopic rod 1-2, and the thermal infrared imager 5 is arranged at the extending tail end of the transverse telescopic rod 1-3; the three-in-one sensor 2 is a temperature, humidity and illumination sensor. The system fixes the thermal infrared imager 5 on the extended bracket, and binds the three-in-one sensor at a lower level about 1-2 meters above the pigsty, thereby ensuring that the collected data is more referential. The support structure can be adjusted in the horizontal direction and the vertical direction. The convenient repeatedly use of taking practices thrift the cost.
The pig body temperature monitoring method (program arranged on a server) based on the thermal infrared technology comprises the following steps:
s1, acquiring environmental information through a three-in-one sensor;
s2, acquiring image information through a thermal infrared imager;
s2-1, identifying pig ears;
s2-2, extracting surface temperature, and taking the highest temperature of the identified pig ear area as the body surface temperature TbStoring the data into a database and marking time;
s3, estimating the body temperature by comprehensively acquiring environmental information and the ear temperature by using the multi-parameter body temperature inversion model;
and S4, storing the data in the server database and feeding the data back to the client for information display.
In step S2-1, in order to ensure effective pig ear region identification, data in an effective hot window is obtained, and a Haar cascade classifier is used for pig ear identification.
The Haar classifier method comprises an AdaBoost algorithm, and uses Haar-like features to quantize the pig ear features, wherein a weak classifier needs to be trained repeatedly to become an optimal weak classifier, and the mathematical structure of the method is as follows:
wherein x represents sub-window image data obtained by step S2-1-2; f represents a characteristic value obtained by step S2-1-3; p represents the direction of indicating the unequal sign, theta represents a threshold value, the four components are equivalent to a decision tree, and a proper classifier threshold value theta is searched in continuous training; f (x) is a feature function, which is known in the specific case.
The weak classifier is equivalent to a decision tree consisting of a sub-window image x, a feature f, p indicating the direction of unequal sign and a threshold value theta, and a proper classifier threshold value, namely a theta value, is searched in continuous training. The weak classifiers are then integrated to form a strong classifier, and the combination method is as follows:
wherein T is the maximum iteration number of training,
ht(x) For the optimal weak classifier obtained in step i, etAnd for the weighted error value after each training, continuously weighting and averaging according to the error rate of the weak classifier, and synthesizing the multistage strong classifier to form a cascade classifier with high accuracy, wherein the cascade classifier is used as a final target Haar classifier. The specific operation flow is shown in fig. 5.
The method has the advantages that the Haar cascade classifier is trained through the images collected in the early stage, and then the Haar cascade classifier is used for pig ear recognition, so that the accuracy of data point acquisition is ensured, and possible interference points are eliminated.
In step S3, the temperature and humidity illumination parameters are taken into the system, and the temperature and humidity illumination parameters are used as important compensation values of the thermal window temperature inversion body temperature, so as to eliminate the interference of the environment on the images acquired by the thermal infrared imager. Therefore, the environmental information and the ear temperature obtained by the multi-parameter body temperature reverse model are used for estimating the body temperature.
In the model, the temperature data in the collected infrared images are extracted, and the value with the highest frequency is selected from a plurality of images. The environment parameters uploaded and stored from the nodes are averaged to obtain the most suitable environment parameters. And fusing the multiple parameters by adopting multivariate linear fitting to obtain a multi-parameter inversion body temperature model, namely the following formula:
Tr＝C+αTi+βHi+γIi+θTb
in the formula, TrThe temperature values of the anus and the intestine which are output by the system are alpha, beta and gamma which are respectively the environmental temperature TiAmbient humidity HiAmbient lighting IiThe ambient temperature T, the ambient temperature TiAmbient humidity HiAmbient lighting IiAll measured by a three-in-one sensor; c is the compensation quantity of the pre-estimated body temperature and is determined by linear fitting; theta is the body surface temperature TbThe theta is obtained by linear fitting, the body surface temperature TbMeasured by a thermal infrared imager.
After the environmental temperature, the environmental humidity, the environmental illumination and the body surface temperature data are input through SPSS software, hypothesis is put forward, multiple logistic regression is established, parameter verification is carried out, and finally the values of the weight coefficients alpha, beta and gamma are obtained.
Wherein, the environmental impact factor p ═ alpha T is obtained by SPSS softwarei+βHi+γIiAll the body surface temperatures T are measuredbAdding the environmental influence factor p to obtain the corrected body surface temperature Tc(ii) a Respectively establishing TcFit straight line and anorectumFitting a straight line by a scatter diagram actually measured by the temperature; fine tuning TcThe fitting straight line of the temperature sensor is used as an inversion temperature straight line, so that the fitting degree of the inversion temperature straight line and the fitting straight line actually measured by the anorectal temperature is maximum; at this time, TcHas a fitting straight line intercept of C value, TcThe slope of the fitted line of (2) is the value of θ.
The data of 100 verification groups are used for error analysis and correlation test, wherein the significance level test p is less than 0.001, and the maximum correlation is achieved. And the relative error is controlled within 3 percent, and the standard parameter can be used as the standard parameter for judging the body temperature.
Based on the method provided by the invention, the pig ear recognition algorithm developed by using the cascade classifier can restrict the temperature points from generating deviation, and the temperature value of the pig ear part is ensured to be acquired. And converting the thermal window temperature value into an approximate anorectal temperature by using a multi-parameter decision-making body temperature estimation model, ensuring that the error rate is lower than 5%, directly acquiring the temperature value of the boar by a user, and taking action in time if abnormal high temperature occurs.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or scope of the invention as defined in the appended claims.
Claims (2)
1. A pig body temperature monitoring method based on a thermal infrared technology is based on a breeding pig body temperature monitoring system, and is characterized in that the system comprises: MCU core chip, image preprocessing module, trinity sensor (2), thermal infrared imager (5), switch, cloud server, mobile terminal, electronic computer, MCU core chip is connected in trinity sensor (2) and environmental information is gathered, thermal infrared imager (5) is connected image preprocessing module and is realized image acquisition, MCU core chip and image preprocessing module upload information to cloud server through the switch, cloud server still connects mobile terminal and electronic computer respectively and distributes information to it, wherein trinity sensor (2) and thermal infrared imager (5) are installed on the supporting structure; the support structure comprises a support (1), a longitudinal adjusting knob (3) and a transverse adjusting knob (4), wherein the support (1) comprises a base (1-1), a longitudinal telescopic rod (1-2) and a transverse telescopic rod (1-3), the bottom of the longitudinal telescopic rod (1-2) is fixed on the base (1-1), the top of the longitudinal telescopic rod (1-2) supports the transverse telescopic rod (1-3), and the longitudinal adjusting knob (3) is arranged on the longitudinal telescopic rod (1-2) and used for adjusting the longitudinal height of the support (1); the transverse adjusting knob (4) is arranged on the transverse telescopic rod (1-3) and is used for adjusting the transverse length of the bracket (1); the three-in-one sensor (2) is arranged at the lower part of the longitudinal telescopic rod (1-2), and the thermal infrared imager (5) is arranged at the extending tail end of the transverse telescopic rod (1-3); the three-in-one sensor (2) is a temperature sensor, a humidity sensor and an illumination sensor; the monitoring method comprises the following steps:
s1, acquiring environmental information through a three-in-one sensor;
s2, acquiring image information through a thermal infrared imager;
s2-1, pig ear recognition:
s2-1-1, inputting an image;
s2-1-2, scanning a window;
s2-1-3, performing feature selection and extraction on the image;
s2-1-4, inputting the extracted information into a classifier, wherein the classifier is formed by the following steps: firstly, selecting a large number of training samples including a positive sample of a pig ear and a negative sample of a non-pig ear, wherein the positive samples are gray level images with the same pixel size; selecting and extracting the characteristics of the samples, and training to form a classifier;
s2-1-5, outputting a classification result;
s2-2, extracting surface temperature, and taking the highest temperature of the identified pig ear area as the body surface temperature TbStoring the data into a database and marking time;
s3, estimating the body temperature by comprehensively acquiring environmental information and the ear temperature by using the multi-parameter body temperature inversion model; the inverse body temperature model in S3 is:
Tr＝C+αTi+βHi+γIi+θTb
in the formula, TrThe anorectal temperature value output by the system is the estimated body temperature, and alpha, beta and gamma are respectively the environmental temperature TiAmbient humidity HiAmbient lighting IiThe ambient temperature T, the ambient temperature TiAmbient humidity HiAmbient lighting IiAll measured by a three-in-one sensor; c is the compensation quantity of the pre-estimated body temperature and is determined by linear fitting; theta is the body surface temperature TbThe theta is obtained by linear fitting, the body surface temperature TbMeasured by a thermal infrared imager;
inputting the data of the environmental temperature, the environmental humidity, the environmental illumination and the body surface temperature through SPSS software, proposing an assumption, establishing multivariate logistic regression, and then carrying out parameter verification to finally obtain the values of the weight coefficients alpha, beta and gamma;
obtaining an environmental impact factor p ═ alpha T through SPSS softwarei+βHi+γIiAll the body surface temperatures T are measuredbAdding an environmental influence factor p to obtain a corrected temperature T of the body surfacec(ii) a Respectively establishing TcFitting straight lines of the model and a scatter diagram fitting straight line actually measured by the anorectal temperature; fine tuning TcThe fitting straight line of the temperature sensor is used as an inversion temperature straight line, so that the fitting degree of the inversion temperature straight line and the fitting straight line actually measured by the anorectal temperature is maximum; at this time, TcHas a fitting straight line intercept of C value, TcThe slope of the fitted straight line is a value theta;
and S4, storing the data in the server database and feeding the data back to the client for information display.
2. The method of claim 1, wherein the classifier training step comprises:
i training the weak classifier repeatedly to become an optimal weak classifier, and the mathematical structure is as follows:
wherein x represents sub-window image data obtained by step S2-1-2; f represents a characteristic value obtained by step S2-1-3; p represents the direction of indicating the unequal sign, m represents the threshold value, the four components are equivalent to a decision tree, and a proper classifier threshold value m is searched in continuous training; (x) is a feature function, which is known in the specific case;
ii, combining the optimal weak classifiers obtained in the step i to form a strong classifier, wherein the combination mode is as follows:
wherein T is the maximum iteration number of training,
ht(x) For the optimal weak classifier obtained in step i, etAnd for the weighted error value after each training, continuously weighting and averaging according to the error rate of the weak classifier, and integrating the multistage strong classifiers to form a cascade classifier with high accuracy, wherein the cascade classifier is used as a final target Haar classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810932394.2A CN109060143B (en) | 2018-08-16 | 2018-08-16 | Pig body temperature monitoring system and method based on thermal infrared technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810932394.2A CN109060143B (en) | 2018-08-16 | 2018-08-16 | Pig body temperature monitoring system and method based on thermal infrared technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109060143A CN109060143A (en) | 2018-12-21 |
| CN109060143B true CN109060143B (en) | 2020-11-24 |
Family
ID=64686107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810932394.2A Active CN109060143B (en) | 2018-08-16 | 2018-08-16 | Pig body temperature monitoring system and method based on thermal infrared technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109060143B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110251096A (en) * | 2019-05-29 | 2019-09-20 | 佛山科学技术学院 | A kind of sows in perinatal period body temperature appraisal procedure and system |
| CN110160655A (en) * | 2019-06-18 | 2019-08-23 | 翔创科技（北京）有限公司 | A kind of amendment infrared thermoviewer is to the method, device and equipment of livestock measurement of bldy temperature |
| CN110333692B (en) * | 2019-07-04 | 2021-09-21 | 南京农业大学 | Pig heating automatic monitoring and diagnosis system based on thermal infrared |
| CN111145205B (en) * | 2019-12-24 | 2022-04-12 | 天津农学院 | Pig body temperature detection method based on infrared image under multiple pig scenes |
| CN111626985A (en) * | 2020-04-20 | 2020-09-04 | 北京农业信息技术研究中心 | Poultry body temperature detection method based on image fusion and poultry house inspection system |
| CN112560336A (en) * | 2020-12-09 | 2021-03-26 | 东莞中融数字科技有限公司 | Livestock internet of things collection body temperature calibration method |
| CN113049113A (en) * | 2021-03-22 | 2021-06-29 | 华东师范大学 | Temperature measuring system and method |
| CN113923619A (en) * | 2021-10-15 | 2022-01-11 | 新希望六和股份有限公司 | Accurate temperature measurement control system |
| CN113875629A (en) * | 2021-11-02 | 2022-01-04 | 华中农业大学 | Live pig body temperature detection device based on thermal imaging |
| CN115307745A (en) * | 2022-08-29 | 2022-11-08 | 河北农业大学 | Automatic sheep body temperature detection system and method based on infrared thermal imager |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398893A (en) * | 2008-10-10 | 2009-04-01 | 北京科技大学 | Adaboost arithmetic improved robust human ear detection method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101793562B (en) * | 2010-01-29 | 2013-04-24 | 中山大学 | Face detection and tracking algorithm of infrared thermal image sequence |
| CN103034154B (en) * | 2012-12-24 | 2015-05-20 | 北京智威宇讯科技有限公司 | Livestock temperature management system and livestock temperature correction method |
| US9866768B1 (en) * | 2013-04-29 | 2018-01-09 | The United States Of America, As Represented By The Secretary Of Agriculture | Computer vision qualified infrared temperature sensor |
| CN105184850A (en) * | 2015-07-02 | 2015-12-23 | 南京斯图刻数码科技有限公司 | Method and system for building and printing animal model through mobile phone camera |
| CN105748046B (en) * | 2016-02-05 | 2018-10-12 | 福建农林大学 | Temperature information monitoring method based on Infrared Thermogram and its system |
| CN108154097A (en) * | 2017-12-20 | 2018-06-12 | 中北大学 | A kind of cage bird health status automatic monitoring sphere wheel trolley and monitoring method |
-
2018
- 2018-08-16 CN CN201810932394.2A patent/CN109060143B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398893A (en) * | 2008-10-10 | 2009-04-01 | 北京科技大学 | Adaboost arithmetic improved robust human ear detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109060143A (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109060143B (en) | Pig body temperature monitoring system and method based on thermal infrared technology | |
| Li et al. | Automated techniques for monitoring the behaviour and welfare of broilers and laying hens: towards the goal of precision livestock farming | |
| CN110333692B (en) | Pig heating automatic monitoring and diagnosis system based on thermal infrared | |
| Mollah et al. | Digital image analysis to estimate the live weight of broiler | |
| CN111696139B (en) | White feather breeding hen group weight estimation system and method based on RGB image | |
| CN110754426B (en) | Method and system for automatically detecting backfat body and automatically feeding animals | |
| KR20190128589A (en) | Method for providing an optimal timing of cattle slaughter based on machine learning model | |
| CN114677624B (en) | Sow delivery intelligent monitoring system based on Yun Bian cooperation | |
| CN114155216A (en) | Pig temperature detection method and device | |
| Huang et al. | Cow tail detection method for body condition score using Faster R-CNN | |
| CN115812634A (en) | Pre-incubation hatching egg fertilization information nondestructive sorting method and device | |
| CN111914685A (en) | Sow oestrus detection method and device, electronic equipment and storage medium | |
| KR20190030877A (en) | Livestock specification management system based on livestock knowledge information | |
| CN114847168A (en) | Intelligent breeding system for animal husbandry | |
| CN112184791A (en) | Yak weight prediction method based on CNN-LSTM neural network | |
| CN108670256B (en) | Cow respiratory rate monitoring system and method | |
| CN116019023A (en) | Electronic information management system and management method | |
| CN117036820B (en) | Pig classification model based on visual image and method thereof | |
| Jebari et al. | Poultry-Edge-AI-IoT System for Real-Time Monitoring and Predicting by Using Artificial Intelligence. | |
| CN113456063A (en) | Artificial intelligence-based dead chicken disease detection system and detection method | |
| Zhou et al. | Detection of abnormal chicken droppings based on improved Faster R-CNN | |
| CN117029904A (en) | Intelligent cage-rearing poultry inspection system | |
| CN115545962A (en) | Crop growth period control method and system based on multi-sensor system | |
| Chen et al. | Establishing an eyeball-weight relationship for Litopenaeus vannamei using machine vision technology | |
| CN201503402U (en) | Thermal infrared image diagnosis system for sclerotinia rot of colza |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |